Search results for: feature noise

Authors: Huayuan Lu, Chunfang Yang, Ma Zhu, Baojun Qi, Yaqiong Qiao, Jiangqian Xu

Abstract:

Image geolocalization has great application prospects in fields such as autonomous driving and virtual/augmented reality. In practical application scenarios, the size of the image to be located is not fixed; it is impractical to train different networks for all possible sizes. When its size does not match the size of the input of the descriptor extraction model, existing image geolocalization methods usually directly scale or crop the image in some common ways. This will result in the loss of some information important to the geolocalization task, thus affecting the performance of the image geolocalization method. For example, excessive down-sampling can lead to blurred building contour, and inappropriate cropping can lead to the loss of key semantic elements, resulting in incorrect geolocation results. To address this problem, this paper designs a learnable image resizer and proposes an arbitrary-sized image geolocation method. (1) The designed learnable image resizer employs the self-attention mechanism to enhance the geometric features of the resized image. Firstly, it applies bilinear interpolation to the input image and its feature maps to obtain the initial resized image and the resized feature maps. Then, SKNet (selective kernel net) is used to approximate the best receptive field, thus keeping the geometric shapes as the original image. And SENet (squeeze and extraction net) is used to automatically select the feature maps with strong contour information, enhancing the geometric features. Finally, the enhanced geometric features are fused with the initial resized image, to obtain the final resized images. (2) The proposed image geolocalization method embeds the above image resizer as a fronting layer of the descriptor extraction network. It not only enables the network to be compatible with arbitrary-sized input images but also enhances the geometric features that are crucial to the image geolocalization task. Moreover, the triplet attention mechanism is added after the first convolutional layer of the backbone network to optimize the utilization of geometric elements extracted by the first convolutional layer. Finally, the local features extracted by the backbone network are aggregated to form image descriptors for image geolocalization. The proposed method was evaluated on several mainstream datasets, such as Pittsburgh30K, Tokyo24/7, and Places365. The results show that the proposed method has excellent size compatibility and compares favorably to recently mainstream geolocalization methods.

Keywords: image geolocalization, self-attention mechanism, image resizer, geometric feature

Procedia PDF Downloads 214

Authors: Xi-Wen Xiao, Tzy-Rong Lin, Chien-Hao Liu

Abstract:

Ventilated acoustic metamaterials have attracted considerable research attention due to their low-frequency absorptions and efficient fluid ventilations. In this research, a wideband acoustic metamaterial with auditory filtering ability and efficient ventilation capacity were proposed. In contrast to a conventional Fano-like resonator, a Fano-like resonator composed of a resonant unit and two nonresonant units with a large opening area of 68% for fluid passages was developed. In addition, the coupling mechanism to improve the narrow bandwidths of conventional Fano-resonance-based meta-materials was included. With a suitable design, the output sound waves of the resonant and nonresonant states were out of phase to achieve sound absorptions in the far fields. Therefore, three-element and five-element coupled Fano-like metamaterials were designed and simulated with the help of the finite element software to obtain the filtering fractional bandwidths of 42.5% and 61.8%, respectively. The proposed approach can be extended to multiple coupled resonators for obtaining ultra-wide bandwidths and can be implemented with 3D printing for practical applications. The research results are expected to be beneficial for sound filtering or noise reductions in duct applications and limited-volume spaces.

Keywords: fano resonance, noise reduction, resonant coupling, sound filtering, ventilated acoustic metamaterial

Procedia PDF Downloads 115

Authors: Anshika Kankane, Dongshik Kang

Abstract:

Marine debris has a significant influence on coastal environments, damaging biodiversity, and causing loss and damage to marine and ocean sector. A functional cost-effective and automatic approach has been used to look up at this problem. Computer vision combined with a deep learning-based model is being proposed to identify and categorize marine debris of seven kinds on different beach locations of Japan. This research compares state-of-the-art deep learning models with a suggested model architecture that is utilized as a feature extractor for debris categorization. The model is being proposed to detect seven categories of litter using a manually constructed debris dataset, with the help of Mask R-CNN for instance segmentation and a shape matching network called HOGShape, which can then be cleaned on time by clean-up organizations using warning notifications of the system. The manually constructed dataset for this system is created by annotating the images taken by fixed KaKaXi camera using CVAT annotation tool with seven kinds of category labels. A pre-trained HOG feature extractor on LIBSVM is being used along with multiple templates matching on HOG maps of images and HOG maps of templates to improve the predicted masked images obtained via Mask R-CNN training. This system intends to timely alert the cleanup organizations with the warning notifications using live recorded beach debris data. The suggested network results in the improvement of misclassified debris masks of debris objects with different illuminations, shapes, viewpoints and litter with occlusions which have vague visibility.

Keywords: computer vision, debris, deep learning, fixed live camera images, histogram of gradients feature extractor, instance segmentation, manually annotated dataset, multiple template matching

Procedia PDF Downloads 107

Authors: P. V. Pramila , V. Mahesh

Abstract:

Pulmonary Function Tests are important non-invasive diagnostic tests to assess respiratory impairments and provides quantifiable measures of lung function. Spirometry is the most frequently used measure of lung function and plays an essential role in the diagnosis and management of pulmonary diseases. However, the test requires considerable patient effort and cooperation, markedly related to the age of patients esulting in incomplete data sets. This paper presents, a nonlinear model built using Multivariate adaptive regression splines and Random forest regression model to predict the missing spirometric features. Random forest based feature selection is used to enhance both the generalization capability and the model interpretability. In the present study, flow-volume data are recorded for N= 198 subjects. The ranked order of feature importance index calculated by the random forests model shows that the spirometric features FVC, FEF 25, PEF,FEF 25-75, FEF50, and the demographic parameter height are the important descriptors. A comparison of performance assessment of both models prove that, the prediction ability of MARS with the `top two ranked features namely the FVC and FEF 25 is higher, yielding a model fit of R2= 0.96 and R2= 0.99 for normal and abnormal subjects. The Root Mean Square Error analysis of the RF model and the MARS model also shows that the latter is capable of predicting the missing values of FEV1 with a notably lower error value of 0.0191 (normal subjects) and 0.0106 (abnormal subjects). It is concluded that combining feature selection with a prediction model provides a minimum subset of predominant features to train the model, yielding better prediction performance. This analysis can assist clinicians with a intelligence support system in the medical diagnosis and improvement of clinical care.

Keywords: FEV, multivariate adaptive regression splines pulmonary function test, random forest

Procedia PDF Downloads 310

Authors: John Lachapelle

Abstract:

Introduction: Neural stimulation is increasingly targeted toward treatment of back pain, PTSD, Parkinson’s disease, and for sensory perception. Sensory recording during stimulation is important in order to examine neural response to stimulation. Most neural amplifiers (headstages) focus on noise efficiency factor (NEF). Conversely, neural headstages need to handle artifacts from several sources including power lines, movement (EMG), and neural stimulation itself. In this work a layered approach to artifact rejection is used to reduce corruption of the neural ENG signal by 60dBv, resulting in recovery of sensory signals in rats and primates that would previously not be possible. Methods: The approach combines analog techniques to reduce and handle unwanted signal amplitudes. The methods include optimized (1) sensory electrode placement, (2) amplifier configuration, and (3) artifact blanking when necessary. The techniques together are like concentric moats protecting a castle; only the wanted neural signal can penetrate. There are two conditions in which the headstage operates: unwanted artifact < 50mV, linear operation, and artifact > 50mV, fast-settle gain reduction signal limiting (covered in more detail in a separate paper). Unwanted Signals at the headstage input: Consider: (a) EMG signals are by nature < 10mV. (b) 60 Hz power line signals may be > 50mV with poor electrode cable conditions; with careful routing much of the signal is common to both reference and active electrode and rejected in the differential amplifier with <50mV remaining. (c) An unwanted (to the neural recorder) stimulation signal is attenuated from stimulation to sensory electrode. The voltage seen at the sensory electrode can be modeled Φ_m=I_o/4πσr. For a 1 mA stimulation signal, with 1 cm spacing between electrodes, the signal is <20mV at the headstage. Headstage ASIC design: The front end ASIC design is designed to produce < 1% THD at 50mV input; 50 times higher than typical headstage ASICs, with no increase in noise floor. This requires careful balance of amplifier stages in the headstage ASIC, as well as consideration of the electrodes effect on noise. The ASIC is designed to allow extremely small signal extraction on low impedance (< 10kohm) electrodes with configuration of the headstage ASIC noise floor to < 700nV/rt-Hz. Smaller high impedance electrodes (> 100kohm) are typically located closer to neural sources and transduce higher amplitude signals (> 10uV); the ASIC low-power mode conserves power with 2uV/rt-Hz noise. Findings: The enhanced neural processing ASIC has been compared with a commercial neural recording amplifier IC. Chronically implanted primates at MGH demonstrated the presence of commercial neural amplifier saturation as a result of large environmental artifacts. The enhanced artifact suppression headstage ASIC, in the same setup, was able to recover and process the wanted neural signal separately from the suppressed unwanted artifacts. Separately, the enhanced artifact suppression headstage ASIC was able to separate sensory neural signals from unwanted artifacts in mouse-implanted peripheral intrafascicular electrodes. Conclusion: Optimizing headstage ASICs allow observation of neural signals in the presence of large artifacts that will be present in real-life implanted applications, and are targeted toward human implantation in the DARPA HAPTIX program.

Keywords: ASIC, biosensors, biomedical signal processing, biomedical sensors

Procedia PDF Downloads 330

Authors: S. Nandagopalan, N. Pradeep

Abstract:

The aim of this paper is to propose a general framework for storing, analyzing, and extracting knowledge from two-dimensional echocardiographic images, color Doppler images, non-medical images, and general data sets. A number of high performance data mining algorithms have been used to carry out this task. Our framework encompasses four layers namely physical storage, object identification, knowledge discovery, user level. Techniques such as active contour model to identify the cardiac chambers, pixel classification to segment the color Doppler echo image, universal model for image retrieval, Bayesian method for classification, parallel algorithms for image segmentation, etc., were employed. Using the feature vector database that have been efficiently constructed, one can perform various data mining tasks like clustering, classification, etc. with efficient algorithms along with image mining given a query image. All these facilities are included in the framework that is supported by state-of-the-art user interface (UI). The algorithms were tested with actual patient data and Coral image database and the results show that their performance is better than the results reported already.

Keywords: active contour, Bayesian, echocardiographic image, feature vector

Procedia PDF Downloads 445

Authors: A. Yamaoka, S. Yukawa

Abstract:

Mind wandering is a mental phenomenon of drifting away from a current task or external environment toward inner thought. This research examines the feature of mind wandering which people who have high creativity and high mental health engage in because it is expected that mind wandering which such kind of people engage in may not induce negative affect, although it can improve creativity. Sixty-seven participants were required to complete questionnaires which measured their creativity and mental health. After that, researchers conducted experience sampling method and measured the details of their mind wandering and the situation when mind wandering was generated in daily life for three days. The result showed that high creative people and high mental health people more think about positive things during mind wandering and less think about negative things. In further research, researchers will examine how to induce positive thought during mind wandering and how to inhibit negative thought during mind wandering. Doing so will contribute to improve creative problem solving without generation of negative affect.

Keywords: creativity, experience sampling method, mental health, mind wandering

Procedia PDF Downloads 173

Authors: Sky Chou, Joseph C. Chen

Abstract:

This paper focuses on using Six Sigma methodologies to improve the surface roughness of a manufactured part produced by the CNC milling machine. It presents a case study where the surface roughness of milled aluminum is required to reduce or eliminate defects and to improve the process capability index C_p and C_pk for a CNC milling process. The six sigma methodology, DMAIC (design, measure, analyze, improve, and control) approach, was applied in this study to improve the process, reduce defects, and ultimately reduce costs. The Taguchi-based six sigma approach was applied to identify the optimized processing parameters that led to the targeted surface roughness specified by our customer. A L₉ orthogonal array was applied in the Taguchi experimental design, with four controllable factors and one non-controllable/noise factor. The four controllable factors identified consist of feed rate, depth of cut, spindle speed, and surface roughness. The noise factor is the difference between the old cutting tool and the new cutting tool. The confirmation run with the optimal parameters confirmed that the new parameter settings are correct. The new settings also improved the process capability index. The purpose of this study is that the Taguchi–based six sigma approach can be efficiently used to phase out defects and improve the process capability index of the CNC milling process.

Keywords: CNC machining, six sigma, surface roughness, Taguchi methodology

Procedia PDF Downloads 242

Authors: Esther Van Andel, Stefanie C. Lange, Maarten M. J. Smulders, Han Zuilhof

Abstract:

False outcomes of diagnostic tests are a major concern in medical health care. To improve the reliability of surface-based diagnostic tests, it is of crucial importance to diminish background signals that arise from the non-specific binding of biomolecules, a process called fouling. The aim is to create surfaces that repel all biomolecules except the molecule of interest. This can be achieved by incorporating antifouling protein repellent coatings in between the sensor surface and it’s recognition elements (e.g. antibodies, sugars, aptamers). Zwitterionic polymer brushes are considered excellent antifouling materials, however, to be able to bind the molecule of interest, the polymer brushes have to be functionalized and so far this was only achieved at the expense of either antifouling or binding capacity. To overcome this limitation, we combined both features into one single monomer: a zwitterionic sulfobetaine, ensuring antifouling capabilities, equipped with a clickable azide moiety which allows for further functionalization. By copolymerizing this monomer together with a standard sulfobetaine, the number of azides (and with that the number of recognition elements) can be tuned depending on the application. First, the clickable azido-monomer was synthesized and characterized, followed by copolymerizing this monomer to yield functionalizable antifouling brushes. The brushes were fully characterized using surface characterization techniques like XPS, contact angle measurements, G-ATR-FTIR and XRR. As a proof of principle, the brushes were subsequently functionalized with biotin via strain-promoted alkyne azide click reactions, which yielded a fully zwitterionic biotin-containing 3D-functionalized coating. The sensing capacity was evaluated by reflectometry using avidin and fibrinogen containing protein solutions. The surfaces showed excellent antifouling properties as illustrated by the complete absence of non-specific fibrinogen binding, while at the same time clear responses were seen for the specific binding of avidin. A great increase in signal-to-noise ratio was observed, even when the amount of functional groups was lowered to 1%, compared to traditional modification of sulfobetaine brushes that rely on a 2D-approach in which only the top-layer can be functionalized. This study was performed on stoichiometric silicon nitride surfaces for future microring resonator based assays, however, this methodology can be transferred to other biosensor platforms which are currently being investigated. The approach presented herein enables a highly efficient strategy for selective binding with retained antifouling properties for improved signal-to-noise ratios in binding assays. The number of recognition units can be adjusted to a specific need, e.g. depending on the size of the analyte to be bound, widening the scope of these functionalizable surface coatings.

Keywords: antifouling, signal-to-noise ratio, surface functionalization, zwitterionic polymer brushes

Procedia PDF Downloads 306

Authors: J. M. Mayoral, M. Anaya

Abstract:

The urban and economic development of cities demands the construction of water use and flood control infrastructure. Likewise, it is necessary to determine the safety level of the structures built with the current standards and if it is necessary to define the reinforcement actions. The foregoing is even more important in structures of great importance, such as dams, since they imply a greater risk for the population in case of failure or undesirable operating conditions (e.g., seepage, cracks, subsidence). This article presents a methodology for determining the seismic integrity of dams in urban areas. From direct measurements of the dynamic properties using geophysical exploration and ambient seismic noise measurements, the seismic integrity of the concrete-faced rockfill dam selected as a case of study is evaluated. To validate the results, two accelerometer stations were installed (e.g., free field and crest of the dam). Once the dynamic properties were determined, three-dimensional finite difference models were developed to evaluate the dam seismic performance for different intensities of movement, considering the site response and soil-structure interaction effects. The seismic environment was determined from the uniform hazard spectra for several return periods. Based on the results obtained, the safety level of the dam against different seismic actions was determined, and the effectiveness of ambient seismic noise measurements in dynamic characterization and subsequent evaluation of the seismic integrity of urban dams was evaluated.

Keywords: risk, seismic, soil-structure interaction, urban dams

Procedia PDF Downloads 118

Authors: K. M. Jananni, R. Nandini

Abstract:

The proposed wireless, inverter type design of a LPG leakage monitoring system aims to provide a smart and safe kitchen. The system detects the LPG gas leak using Nano-sensors and alerts the concerned individual through GSM system. The system uses two sensors, one attached to the chimney and other to the regulator of the LPG cylinder. Upon a leakage being detected, the sensor at the regulator actuates the system to cut off the gas supply immediately using a solenoid control valve. The sensor at the chimney checks for the permissible level of LPG mix in the air and when the level exceeds the threshold, the system sends an automatic SMS to the numbers saved. Further the sensor actuates the mini suction system fixed at the chimney within 20 seconds of a leakage to suck out the gas until the level falls well below the threshold. As a safety measure, an automatic window opening and alarm feature is also incorporated into the system. The key feature of this design is that the system is provided with a special inverter designed to make the device function effectively even during power failures. In this paper, utilization of sensors in the kitchen area is discussed and this gives the proposed architecture for real time field monitoring with a PIC Micro-controller.

Keywords: nano sensors, global system for mobile communication, GSM, micro controller, inverter

Procedia PDF Downloads 473

Authors: Radhika Ranjan Roy

Abstract:

Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.

Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve

Procedia PDF Downloads 78

Authors: Abdullah Alnutayfat, Alexander Sutin, Dong Liu

Abstract:

Wind turbine has become one of the most popular energy productions. However, failure of blades and maintenance costs evolve into significant issues in the wind power industry, so it is essential to detect the initial blade defects to avoid the collapse of the blades and structure. This paper aims to apply modulation of high-frequency blade vibrations by low-frequency blade rotation, which is close to the known Vibro-Acoustic Modulation (VAM) method. The high-frequency wideband blade vibration is produced by the interaction of the surface blades with the environment air turbulence, and the low-frequency modulation is produced by alternating bending stress due to gravity. The low-frequency load of rotational wind turbine blades ranges between 0.2-0.4 Hz and can reach up to 2 Hz for strong wind. The main difference between this study and previous ones on VAM methods is the use of a wideband vibration signal from the blade's natural vibrations. Different features of the vibroacoustic modulation are considered using a simple model of breathing crack. This model considers the simple mechanical oscillator, where the parameters of the oscillator are varied due to low-frequency blade rotation. During the blade's operation, the internal stress caused by the weight of the blade modifies the crack's elasticity and damping. The laboratory experiment using steel samples demonstrates the possibility of VAM using a probe wideband noise signal. A cycle load with a small amplitude was used as a pump wave to damage the tested sample, and a small transducer generated a wideband probe wave. The received signal demodulation was conducted using the Detecting of Envelope Modulation on Noise (DEMON) approach. In addition, the experimental results were compared with the modulation index (MI) technique regarding the harmonic pump wave. The wideband and traditional VAM methods demonstrated similar sensitivity for earlier detection of invisible cracks. Importantly, employing a wideband probe signal with the DEMON approach speeds up and simplifies testing since it eliminates the need to conduct tests repeatedly for various harmonic probe frequencies and to adjust the probe frequency.

Keywords: vibro-acoustic modulation, detecting of envelope modulation on noise, damage, turbine blades

Procedia PDF Downloads 99

Authors: Sandeep Santosh, O. P. Sahu

Abstract:

In this paper, performance comparison of wideband covariance matrix sparse representation (W-CMSR) method with other existing wideband Direction of Arrival (DOA) estimation methods has been made.W-CMSR relies less on a priori information of the incident signal number than the ordinary subspace based methods.Consider the perturbation free covariance matrix of the wideband array output. The diagonal covariance elements are contaminated by unknown noise variance. The covariance matrix of array output is conjugate symmetric i.e its upper right triangular elements can be represented by lower left triangular ones.As the main diagonal elements are contaminated by unknown noise variance,slide over them and align the lower left triangular elements column by column to obtain a measurement vector.Simulation results for W-CMSR are compared with simulation results of other wideband DOA estimation methods like Coherent signal subspace method (CSSM), Capon, l1-SVD, and JLZA-DOA. W-CMSR separate two signals very clearly and CSSM, Capon, L1-SVD and JLZA-DOA fail to separate two signals clearly and an amount of pseudo peaks exist in the spectrum of L1-SVD.

Keywords: W-CMSR, wideband direction of arrival (DOA), covariance matrix, electrical and computer engineering

Procedia PDF Downloads 471

Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.

Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine

Procedia PDF Downloads 240

Authors: Wade Ghribi, Abdelmoty M. Ahmed, Ahmed Said Badawy, Belgacem Bouallegue

Abstract:

In higher education institutions, the most pressing priority is to improve student performance and retention. Large volumes of student data are used in Educational Data Mining techniques to find new hidden information from students' learning behavior, particularly to uncover the early symptom of at-risk pupils. On the other hand, data with noise, outliers, and irrelevant information may provide incorrect conclusions. By identifying features of students' data that have the potential to improve performance prediction results, comparing and identifying the most appropriate ensemble learning technique after preprocessing the data, and optimizing the hyperparameters, this paper aims to develop a reliable students' performance prediction model for Higher Education Institutions. Data was gathered from two different systems: a student information system and an e-learning system for undergraduate students in the College of Computer Science of a Saudi Arabian State University. The cases of 4413 students were used in this article. The process includes data collection, data integration, data preprocessing (such as cleaning, normalization, and transformation), feature selection, pattern extraction, and, finally, model optimization and assessment. Random Forest, Bagging, Stacking, Majority Vote, and two types of Boosting techniques, AdaBoost and XGBoost, are ensemble learning approaches, whereas Decision Tree, Support Vector Machine, and Artificial Neural Network are supervised learning techniques. Hyperparameters for ensemble learning systems will be fine-tuned to provide enhanced performance and optimal output. The findings imply that combining features of students' behavior from e-learning and students' information systems using Majority Vote produced better outcomes than the other ensemble techniques.

Keywords: educational data mining, student performance prediction, e-learning, classification, ensemble learning, higher education

Procedia PDF Downloads 108

Authors: Sky Chou, Joseph C. Chen

Abstract:

This paper focuses on using six sigma methodologies to reach the desired shrinkage of a manufactured high-density polyurethane (HDPE) part produced by the injection molding machine. It presents a case study where the correct shrinkage is required to reduce or eliminate defects and to improve the process capability index Cp and Cpk for an injection molding process. To improve this process and keep the product within specifications, the six sigma methodology, design, measure, analyze, improve, and control (DMAIC) approach, was implemented in this study. The six sigma approach was paired with the Taguchi methodology to identify the optimized processing parameters that keep the shrinkage rate within the specifications by our customer. An L9 orthogonal array was applied in the Taguchi experimental design, with four controllable factors and one non-controllable/noise factor. The four controllable factors identified consist of the cooling time, melt temperature, holding time, and metering stroke. The noise factor is the difference between material brand 1 and material brand 2. After the confirmation run was completed, measurements verify that the new parameter settings are optimal. With the new settings, the process capability index has improved dramatically. The purpose of this study is to show that the six sigma and Taguchi methodology can be efficiently used to determine important factors that will improve the process capability index of the injection molding process.

Keywords: injection molding, shrinkage, six sigma, Taguchi parameter design

Procedia PDF Downloads 178

Authors: S. Nandagopalan, N. Pradeep

Abstract:

The aim of this paper is to propose a general framework for storing, analyzing, and extracting knowledge from two-dimensional echocardiographic images, color Doppler images, non-medical images, and general data sets. A number of high performance data mining algorithms have been used to carry out this task. Our framework encompasses four layers namely physical storage, object identification, knowledge discovery, user level. Techniques such as active contour model to identify the cardiac chambers, pixel classification to segment the color Doppler echo image, universal model for image retrieval, Bayesian method for classification, parallel algorithms for image segmentation, etc., were employed. Using the feature vector database that have been efficiently constructed, one can perform various data mining tasks like clustering, classification, etc. with efficient algorithms along with image mining given a query image. All these facilities are included in the framework that is supported by state-of-the-art user interface (UI). The algorithms were tested with actual patient data and Coral image database and the results show that their performance is better than the results reported already.

Keywords: active contour, bayesian, echocardiographic image, feature vector

Procedia PDF Downloads 420

Authors: Pamir Gogoi, Ratree Wayland

Abstract:

This study investigates the acoustic measures of breathiness when coarticulated with nasality. The acoustic correlates of breathiness and nasality that has already been well established after years of empirical research. Some of these acoustic parameters - like low frequency peaks and wider bandwidths- are common for both nasal and breathy voice. Therefore, it is likely that these parameters interact when a sound is coarticulated with breathiness and nasality. This leads to the hypothesis that the acoustic parameters, which usually act as robust cues in differentiating between breathy and modal voice, might not be reliable cues for differentiating between breathy and modal voice when breathiness is coarticulated with nasality. The effect of nasality on the perception of breathiness has been explored in earlier studies using synthesized speech. The results showed that perceptually, nasality and breathiness do interact. The current study investigates if a similar pattern is observed in natural speech. The study is conducted on Marathi, an Indo-Aryan language which has a three-way contrast between nasality and breathiness. That is, there is a phonemic distinction between nasals, breathy voice and breathy-nasals. Voice quality parameters like – H1-H2 (Difference between the amplitude of first and second harmonic), H1-A3 (Difference between the amplitude of first harmonic and third formant, CPP (Cepstral Peak Prominence), HNR (Harmonics to Noise ratio) and B1 (Bandwidth of first formant) were extracted. Statistical models like linear mixed effects regression and Random Forest classifiers show that measures that capture the noise component in the signal- like CPP and HNR- can classify breathy voice from modal voice better than spectral measures when breathy voice is coarticulated with nasality.

Keywords: breathiness, marathi, nasality, voice quality

Procedia PDF Downloads 96

Authors: Vinod Ponnagandla, Brenton McLaury, Siamack Shirazi

Abstract:

Sand production can lead to deposition of particles or erosion. Low production rates resulting in deposition can partially clog systems and cause under deposit corrosion. Commercially available nonintrusive acoustic sand detectors are attractive as they claim to detect sand production. Acoustic sand detectors are used during oil and gas production; however, operators often do not know the threshold detection limits of these devices. It is imperative to know the detection limits to appropriately plan for cleaning of separation equipment or examine risk of erosion. These monitors are based on detecting the acoustic signature of sand as the particles impact the pipe walls. The objective of this work is to determine threshold detection limits for acoustic sand monitors that are commercially available. The minimum threshold sand concentration that can be detected in a pipe are determined as a function of flowing gas and liquid velocities. A large scale flow loop with a 4-inch test section is utilized. Commercially available sand monitors (ClampOn and Roxar) are evaluated for different flow regimes, sand sizes and pipe orientation (vertical and horizontal). The manufacturers’ recommend that the monitors be placed on a bend to maximize the number of particle impacts, so results are shown for monitors placed at 45 and 90 degree positions in a bend. Acoustic sand monitors that clamp to the outside of pipe are passive and listen for solid particle impact noise. The threshold sand rate is calculated by eliminating the background noise created by the flow of gas and liquid in the pipe for various flow regimes that are generated in horizontal and vertical test sections. The average sand sizes examined are 150 and 300 microns. For stratified and bubbly flows the threshold sand rates are much higher than other flow regimes such as slug and annular flow regimes that are investigated. However, the background noise generated by slug flow regime is very high and cause a high uncertainty in detection limits. The threshold sand rates for annular flow and dry gas conditions are the lowest because of high gas velocities. The effects of monitor placement around elbows that are in vertical and horizontal pipes are also examined for 150 micron. The results show that the threshold sand rates that are detected in vertical orientation are generally lower for all various flow regimes that are investigated.

Keywords: acoustic monitor, sand, multiphase flow, threshold

Procedia PDF Downloads 407

Authors: Hao Wang, Shengchun Wang, Weidong Wang

Abstract:

On the influence of train vibration and environmental noise on the measurement of track wear, we proposed a method for automatic extraction of circular arc on the inner or outer side of the rail waist and achieved the high-precision registration of rail profile. Firstly, a polynomial fitting method based on truncated residual histogram was proposed to find the optimal fitting curve of the profile and reduce the influence of noise on profile curve fitting. Then, based on the curvature distribution characteristics of the fitting curve, the interval search algorithm based on dynamic window’s maximum curvature entropy was proposed to realize the automatic segmentation of small circular arc. At last, we fit two circle centers as matching reference points based on small circular arcs on both sides and realized the alignment from the measured profile to the standard designed profile. The static experimental results show that the mean and standard deviation of the method are controlled within 0.01mm with small measurement errors and high repeatability. The dynamic test also verified the repeatability of the method in the train-running environment, and the dynamic measurement deviation of rail wear is within 0.2mm with high repeatability.

Keywords: curvature entropy, profile registration, rail wear, structured light, train-running

Procedia PDF Downloads 260

Authors: Mattias Bergstrom

Abstract:

Significance of the Study: This research will provide new insights into the risks with digital embedded infrastructure. Through this research, we will analyze each risk and its potential negation strategies, especially for AI and autonomous automation. Moreover, the analysis that is presented in this paper will convey valuable information for future research that can create more stable, secure, and efficient autonomous systems. To learn and understand the risks, a large IoT system was envisioned, and risks with hardware, tampering, and cyberattacks were collected, researched, and evaluated to create a comprehensive understanding of the potential risks. Potential solutions have then been evaluated on an open source IoT hardware setup. This list shows the identified passive and active risks evaluated in the research. Passive Risks: (1) Hardware failures- Critical Systems relying on high rate data and data quality are growing; SCADA systems for infrastructure are good examples of such systems. (2) Hardware delivers erroneous data- Sensors break, and when they do so, they don’t always go silent; they can keep going, just that the data they deliver is garbage, and if that data is not filtered out, it becomes disruptive noise in the system. (3) Bad Hardware injection- Erroneous generated sensor data can be pumped into a system by malicious actors with the intent to create disruptive noise in critical systems. (4) Data gravity- The weight of the data collected will affect Data-Mobility. (5) Cost inhibitors- Running services that need huge centralized computing is cost inhibiting. Large complex AI can be extremely expensive to run. Active Risks: Denial of Service- It is one of the most simple attacks, where an attacker just overloads the system with bogus requests so that valid requests disappear in the noise. Malware- Malware can be anything from simple viruses to complex botnets created with specific goals, where the creator is stealing computer power and bandwidth from you to attack someone else. Ransomware- It is a kind of malware, but it is so different in its implementation that it is worth its own mention. The goal with these pieces of software is to encrypt your system so that it can only be unlocked with a key that is held for ransom. DNS spoofing- By spoofing DNS calls, valid requests and data dumps can be sent to bad destinations, where the data can be extracted for extortion or to corrupt and re-inject into a running system creating a data echo noise loop. After testing multiple potential solutions. We found that the most prominent solution to these risks was to use a Peer 2 Peer consensus algorithm over a blockchain to validate the data and behavior of the devices (sensors, storage, and computing) in the system. By the devices autonomously policing themselves for deviant behavior, all risks listed above can be negated. In conclusion, an Internet middleware that provides these features would be an easy and secure solution to any future autonomous IoT deployments. As it provides separation from the open Internet, at the same time, it is accessible over the blockchain keys.

Keywords: IoT, security, infrastructure, SCADA, blockchain, AI

Procedia PDF Downloads 107

Authors: Chandra Gupt Porwal

Abstract:

Excessive vibration means increased wear, increased repair efforts, bad product selection & quality and high energy consumption. This may be sometimes experienced by cavitation or suction/discharge re-circulation which could occur only when net positive suction head available NPSHA drops below the net positive suction head required NPSHR. Cavitation can cause axial surging if it is excessive, will damage mechanical seals, bearings, possibly other pump components frequently and shorten the life of the impeller. Efforts have been made to explain Suction Energy (SE), Specific Speed (Ns), Suction Specific Speed (Nss), NPSHA, NPSHR & their significance, possible reasons of cavitation /internal re-circulation, its diagnostics and remedial measures to arrest and prevent cavitation in this paper. A case study is presented by the author highlighting that the root cause of unwanted noise and vibration is due to cavitation, caused by high specific speeds or inadequate net- positive suction head available which results in damages to material surfaces of impeller & suction bells and degradation of machine performance, its capacity and efficiency too. The author strongly recommends revisiting the technical specifications of CW pumps to provide sufficient NPSH margin ratios > 1.5, for future projects and Nss be limited to 8500 -9000 for cavitation free operation.

Keywords: best efficiency point (BEP), net positive suction head NPSHA, NPSHR, specific speed NS, suction specific speed NSS

Procedia PDF Downloads 254

Authors: Hala Zaghloul, Taymoor Nazmy

Abstract:

One of the great challenges of the 21st century is to build a robot that can perceive and act within its environment and communicate with people, while also exhibiting the cognitive capabilities that lead to performance like that of people. The Pulse Coupled Neural Network, PCNN, is a relative new ANN model that derived from a neural mammal model with a great potential in the area of image processing as well as target recognition, feature extraction, speech recognition, combinatorial optimization, compressed encoding. PCNN has unique feature among other types of neural network, which make it a candid to be an important approach for perceiving in cognitive systems. This work show and emphasis on the potentials of PCNN to perform different tasks related to image processing. The main drawback or the obstacle that prevent the direct implementation of such technique, is the need to find away to control the PCNN parameters toward perform a specific task. This paper will evaluate the performance of PCNN standard model for processing images with different properties, and select the important parameters that give a significant result, also, the approaches towards find a way for the adaptation of the PCNN parameters to perform a specific task.

Keywords: cognitive system, image processing, segmentation, PCNN kernels

Procedia PDF Downloads 280

Authors: Xiang Shijie, Zhou Dong, Tian Dan

Abstract:

Speaker recognition is a crucial task in the field of speech processing, aimed at identifying individuals based on their vocal characteristics. However, existing speaker recognition methods face numerous challenges. Traditional methods primarily rely on audio signals, which often suffer from limitations in noisy environments, variations in speaking style, and insufficient sample sizes. Additionally, relying solely on audio features can sometimes fail to capture the unique identity of the speaker comprehensively, impacting recognition accuracy. To address these issues, we propose a multi-modal network architecture that simultaneously processes both audio and text signals. By gradually integrating audio and text features, we leverage the strengths of both modalities to enhance the robustness and accuracy of speaker recognition. Our experiments demonstrate significant improvements with this multi-modal approach, particularly in complex environments, where recognition performance has been notably enhanced. Our research not only highlights the limitations of current speaker recognition methods but also showcases the effectiveness of multi-modal fusion techniques in overcoming these limitations, providing valuable insights for future research.

Keywords: feature fusion, memory network, multimodal input, speaker recognition

Procedia PDF Downloads 33

Authors: Rajpal Kaur, Pooja Choudhary

Abstract:

Biometrics, which refers to identifying an individual based on his or her physiological or behavioral characteristics, has the capabilities to the reliably distinguish between an authorized person and an imposter. The Signature recognition systems can categorized as offline (static) and online (dynamic). This paper presents Surf Feature based recognition of offline signatures system that is trained with low-resolution scanned signature images. The signature of a person is an important biometric attribute of a human being which can be used to authenticate human identity. However the signatures of human can be handled as an image and recognized using computer vision and HMM techniques. With modern computers, there is need to develop fast algorithms for signature recognition. There are multiple techniques are defined to signature recognition with a lot of scope of research. In this paper, (static signature) off-line signature recognition & verification using surf feature with HMM is proposed, where the signature is captured and presented to the user in an image format. Signatures are verified depended on parameters extracted from the signature using various image processing techniques. The Off-line Signature Verification and Recognition is implemented using Mat lab platform. This work has been analyzed or tested and found suitable for its purpose or result. The proposed method performs better than the other recently proposed methods.

Keywords: offline signature verification, offline signature recognition, signatures, SURF features, HMM

Procedia PDF Downloads 384

Authors: Naser Safdarian, Nader Jafarnia Dabanloo

Abstract:

In this paper we used four features i.e. Q-wave integral, QRS complex integral, T-wave integral and total integral as extracted feature from normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our research we focused on detection and localization of MI in standard ECG. We use the Q-wave integral and T-wave integral because this feature is important impression in detection of MI. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI. Because these methods have good accuracy for classification of normal and abnormal signals. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 80% for accuracy in test data for localization and over 95% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve accuracy of classification by adding more features in this method. A simple method based on using only four features which extracted from standard ECG is presented which has good accuracy in MI localization.

Keywords: ECG signal processing, myocardial infarction, features extraction, pattern recognition

Procedia PDF Downloads 456

Authors: Kay Thinzar Phu, Lwin Lwin Oo

Abstract:

In an intelligent transport system and advanced driver assistance system, the developing of real-time traffic sign detection and recognition (TSDR) system plays an important part in recent research field. There are many challenges for developing real-time TSDR system due to motion artifacts, variable lighting and weather conditions and situations of traffic signs. Researchers have already proposed various methods to minimize the challenges problem. The aim of the proposed research is to develop an efficient and effective TSDR in real time. This system proposes an adaptive thresholding method based on RGB color for traffic signs detection and new features for traffic signs recognition. In this system, the RGB color thresholding is used to detect the blue and yellow color traffic signs regions. The system performs the shape identify to decide whether the output candidate region is traffic sign or not. Lastly, new features such as termination points, bifurcation points, and 90’ angles are extracted from validated image. This system uses Myanmar Traffic Sign dataset.

Keywords: adaptive thresholding based on RGB color, blue color detection, feature extraction, yellow color detection

Procedia PDF Downloads 313

Authors: Jamshaid Ul Rahman, Faiza Makhdoom, Dianchen Lu

Abstract:

Activation functions play a decisive role in determining the capacity of Deep Neural Networks (DNNs) as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions primarily focused on the utility of monotonic or non-oscillatory functions, until Growing Cosine Unit (GCU) broke the taboo for a number of applications. In this paper, a Convolutional Neural Network (CNN) model named as ASU-CNN is proposed which utilizes recently designed activation function ASU across its layers. The effect of this non-monotonic and oscillatory function is inspected through feature map visualizations from different convolutional layers. The optimization of proposed network is offered by Adam with a fine-tuned adjustment of learning rate. The network achieved promising results on both training and testing data for the classification of CIFAR-10. The experimental results affirm the computational feasibility and efficacy of the proposed model for performing tasks related to the field of computer vision.

Keywords: amplifying sine unit, activation function, convolutional neural networks, oscillatory activation, image classification, CIFAR-10

Procedia PDF Downloads 111

Authors: Alla Levina, Sergey Taranov

Abstract:

The classical approach to the providing noise immunity and integrity of information that process in computing devices and communication channels is to use linear codes. Linear codes have fast and efficient algorithms of encoding and decoding information, but this codes concentrate their detect and correct abilities in certain error configurations. To protect against any configuration of errors at predetermined probability can robust codes. This is accomplished by the use of perfect nonlinear and almost perfect nonlinear functions to calculate the code redundancy. The paper presents the error-correcting coding scheme using biorthogonal wavelet transform. Wavelet transform applied in various fields of science. Some of the wavelet applications are cleaning of signal from noise, data compression, spectral analysis of the signal components. The article suggests methods for constructing linear codes based on wavelet decomposition. For developed constructions we build generator and check matrix that contain the scaling function coefficients of wavelet. Based on linear wavelet codes we develop robust codes that provide uniform protection against all errors. In article we propose two constructions of robust code. The first class of robust code is based on multiplicative inverse in finite field. In the second robust code construction the redundancy part is a cube of information part. Also, this paper investigates the characteristics of proposed robust and linear codes.

Keywords: robust code, linear code, wavelet decomposition, scaling function, error masking probability

Procedia PDF Downloads 489